Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1348 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0786. Min Act: -0.0005

Data Index: 469797 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0696. Min Act: -0.0005

Data Index: 285802 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0659. Min Act: -0.0005

Data Index: 390126 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0663. Min Act: -0.0005

Data Index: 377645 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0708. Min Act: -0.0005

Data Index: 99874 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0645. Min Act: -0.0005

Data Index: 152252 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0644. Min Act: -0.0005

Data Index: 900052 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0598. Min Act: -0.0005

Data Index: 660045 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0575. Min Act: -0.0005

Data Index: 727316 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0589. Min Act: -0.0005

Data Index: 169482 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0591. Min Act: -0.0005

Data Index: 1006497 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0610. Min Act: -0.0005

Data Index: 1065929 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0602. Min Act: -0.0005

Data Index: 1137187 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0585. Min Act: -0.0005

Data Index: 1109070 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0630. Min Act: -0.0005

Data Index: 807024 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0627. Min Act: -0.0005

Data Index: 996418 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0582. Min Act: -0.0005

Data Index: 722739 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0603. Min Act: -0.0005

Data Index: 1306845 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0622. Min Act: -0.0005

Data Index: 121847 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0595. Min Act: -0.0005

Data Index: 527318 (C4 (Web Text))

Max Activating Token Index: 626